科研之友
微信
新浪微博
Facebook
分享链接
摘要
As a successively and locally plastic deformation process, backward ball spinning is applied for the purpose of manufacturing thin-walled tubular part with longitudinal inner ribs. Obtaining the desired inner ribs is one of the most critical tasks in backward ball spinning of thin-walled tubular part with longitudinal inner ribs and the formability of inner ribs depends greatly on the process parameters, such as ball diameter, feed ratio, wall thickness reduction and wall thickness of tubular blank. As a nonlinear dynamics system simulating structure and function of biological neural network in the human brain, back-propagation artificial neural network (BPANN) is used in backward ball spinning of thin-walled tubular part with longitudinal inner ribs. The attractiveness of BPANN comes from its remarkable information processing characteristics pertinent mainly to nonlinearity, adaptability, high parallelism, learning capability, fault and noise tolerance so that it can be more efficient in solving complex and nonlinear optimization problems in backward ball spinning of thin-walled tubular parts with longitudinal inner ribs. Not only can BPANN successfully predict the formability of the inner ribs, but it can simulate the influences of the process parameters on the height of inner ribs as well. In the end, the process parameters are matched so rationally that the desired spun parts can be obtained.
